AI Paper Atlas

Research map / Image generation / Super-resolution

Blind Super-Resolution via Meta-Learning and Markov Chain Monte Carlo Simulation

Jingyuan Xia, Zhixiong Yang, Shengxi Li, Shuanghui Zhang, Yaowen Fu, Denız Gündüz, Xiang Li

TPAMI 2024 · Image generation › Super-resolution · approach: Blind super-resolution · 80 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MLMC meta-learning plus MCMC kernel estimation instead of BSRDMBSRDM · Set5 x2PSNR: 30.56 -> 31.61Improved
use MLMC instead of FKP-DIPFKP-DIP · Urban100 x4PSNR: 22.89 -> 23.83Improved
use MLMC instead of BSRDMBSRDM · Set5 x4PSNR: 27.81 -> 28.87Improved
use MLMC kernel estimate with USRNet instead of MANet kernelMANet+USRNet · Set5 x4PSNR: 29.87 -> 30.31Improved
use MLMC instead of BSRDM on out-of-distribution kernelsBSRDM · Set14 x2kernel PSNR: 42.53 -> 52.32Improved
use MLMC instead of BSRDM under 3.92% image noiseBSRDM · Set14 x4image PSNR: 20.99 -> 24.96Improved
run meta-learning optimization with interval P>=2 instead of withoutMLMC · Set5PSNRImproved
vary number of Monte Carlo sampling times TMLMC · Set5PSNRNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy